hydroanomaly 1.2.0__py3-none-any.whl → 1.2.1__py3-none-any.whl

hydroanomaly/__init__.py

@@ -10,7 +10,7 @@ A simple Python package with just 3 modules:
 That's it - nothing else!
 """
 
-__version__ = "1.2.0"
+__version__ = "1.2.1"
 __author__ = "Ehsan Kahrizi (Ehsan.kahrizi@usu.edu)"
 
 # Import the 3 simple modules

hydroanomaly/ml.py

@@ -8,20 +8,20 @@ import matplotlib.pyplot as plt
 
 # ============= Helper Functions =========================================================================
 def match_nearest(row, usgs):
-    target_time = row['date']
-    same_day = usgs[usgs['date'] == target_time.date()]
+    target_time = row['datetime']
+    same_day = usgs[usgs['datetime'] == target_time.datetime()]
     if same_day.empty:
         return np.nan
     delta = (same_day['datetime'] - target_time).abs()
-    return same_day.loc[delta.idxmin(), 'Turbidity']
+    return same_day.loc[delta.idxmin(), 'turbidity']
 
 
 
 # ============= Preprocessing and Feature Engineering ========================================================
 def preprocess_data(sentinel, usgs):
     # Add matched turbidity
-    sentinel['Turbidity'] = sentinel.apply(lambda row: match_nearest(row, usgs), axis=1)
-    df = sentinel.dropna(subset=['Turbidity'])
+    sentinel['turbidity'] = sentinel.apply(lambda row: match_nearest(row, usgs), axis=1)
+    df = sentinel.dropna(subset=['turbidity'])
 
     # Water pixels filtering
     if 'SCL' in df.columns and (df['SCL'] == 6).sum() > 0:
@@ -33,15 +33,15 @@ def preprocess_data(sentinel, usgs):
     df['NDWI'] = (df['B3'] - df['B8']) / (df['B3'] + df['B8'])
     df['NDSI'] = (df['B3'] - df['B11']) / (df['B3'] + df['B11'])
 
-    df = df.sort_values('date').reset_index(drop=True)
-    df['Turbidity_diff1'] = df['Turbidity'].diff()
-    df['Turbidity_diff2'] = df['Turbidity_diff1'].diff()
-    thresh = 2 * df['Turbidity_diff2'].std()
-    df['spike'] = (df['Turbidity_diff2'].abs() > thresh).astype(int)
+    df = df.sort_values('datetime').reset_index(drop=True)
+    df['turbidity_diff1'] = df['turbidity'].diff()
+    df['turbidity_diff2'] = df['turbidity_diff1'].diff()
+    thresh = 2 * df['turbidity_diff2'].std()
+    df['spike'] = (df['turbidity_diff2'].abs() > thresh).astype(int)
     df = df.dropna()
 
     # Class label
-    df['Classe'] = (df['Turbidity'] > 20).astype(int)
+    df['Classe'] = (df['turbidity'] > 20).astype(int)
     return df, bands
 
 
@@ -52,7 +52,7 @@ def run_oneclass_svm(sentinel, usgs, plot=True):
     Returns: DataFrame with predictions, and best model parameters.
     """
     df, bands = preprocess_data(sentinel, usgs)
-    features = bands + ['NDVI','NDWI','NDSI','Turbidity_diff1','Turbidity_diff2','spike']
+    features = bands + ['NDVI','NDWI','NDSI','turbidity_diff1','turbidity_diff2','spike']
     X = df[features].fillna(df[features].mean()).values
     y = df['Classe'].values
 
@@ -87,14 +87,14 @@ def run_oneclass_svm(sentinel, usgs, plot=True):
         df_out['predicted'] = best_y_pred
         if plot:
             plt.figure(figsize=(15,6))
-            plt.plot(df_out['date'], df_out['Turbidity'], label='Turbidity', color='blue')
-            plt.scatter(df_out[df_out['Classe']==1]['date'], df_out[df_out['Classe']==1]['Turbidity'],
+            plt.plot(df_out['datetime'], df_out['turbidity'], label='turbidity', color='blue')
+            plt.scatter(df_out[df_out['Classe']==1]['datetime'], df_out[df_out['Classe']==1]['turbidity'],
                         color='red', marker='x', label='True Anomaly', s=100)
-            plt.scatter(df_out[df_out['predicted']==1]['date'], df_out[df_out['predicted']==1]['Turbidity'],
+            plt.scatter(df_out[df_out['predicted']==1]['datetime'], df_out[df_out['predicted']==1]['turbidity'],
                         edgecolors='orange', facecolors='none', marker='o', label='Predicted Anomaly', s=80)
             plt.title("True vs Predicted Anomalies (OneClassSVM)")
-            plt.xlabel("Date")
-            plt.ylabel("Turbidity")
+            plt.xlabel("datetime")
+            plt.ylabel("turbidity")
             plt.legend()
             plt.grid(True)
             plt.tight_layout()
@@ -112,7 +112,7 @@ def run_isolation_forest(sentinel, usgs, plot=True):
     Returns: DataFrame with predictions, and best model parameters.
     """
     df, bands = preprocess_data(sentinel, usgs)
-    features = bands + ['NDVI','NDWI','NDSI','Turbidity_diff1','Turbidity_diff2','spike']
+    features = bands + ['NDVI','NDWI','NDSI','turbidity_diff1','turbidity_diff2','spike']
     X = df[features].fillna(df[features].mean()).values
     y = df['Classe'].values
 
@@ -152,14 +152,14 @@ def run_isolation_forest(sentinel, usgs, plot=True):
         df_out['predicted'] = best_y_pred
         if plot:
             plt.figure(figsize=(15,6))
-            plt.plot(df_out['date'], df_out['Turbidity'], label='Turbidity', color='blue')
-            plt.scatter(df_out[df_out['Classe']==1]['date'], df_out[df_out['Classe']==1]['Turbidity'],
+            plt.plot(df_out['datetime'], df_out['turbidity'], label='turbidity', color='blue')
+            plt.scatter(df_out[df_out['Classe']==1]['datetime'], df_out[df_out['Classe']==1]['turbidity'],
                         color='red', marker='x', label='True Anomaly', s=100)
-            plt.scatter(df_out[df_out['predicted']==1]['date'], df_out[df_out['predicted']==1]['Turbidity'],
+            plt.scatter(df_out[df_out['predicted']==1]['datetime'], df_out[df_out['predicted']==1]['turbidity'],
                         edgecolors='orange', facecolors='none', marker='o', label='Predicted Anomaly', s=80)
             plt.title("True vs Predicted Anomalies (Isolation Forest)")
-            plt.xlabel("Date")
-            plt.ylabel("Turbidity")
+            plt.xlabel("datetime")
+            plt.ylabel("turbidity")
             plt.legend()
             plt.grid(True)
             plt.tight_layout()

hydroanomaly/sentinel_bands.py

@@ -79,14 +79,14 @@ def get_sentinel_bands_gee(
     s2_masked = s2.map(dynamic_scl_mask)
 
     def extract_features(image):
-        date = image.date().format('YYYY-MM-dd HH:mm:ss')
+        datetime = image.date().format('YYYY-MM-dd HH:mm:ss')
         values = image.reduceRegion(
             reducer=ee.Reducer.mean(),
             geometry=buffered_point,
             scale=20,
             maxPixels=1e8
         )
-        return ee.Feature(None, values.set('date', date))
+        return ee.Feature(None, values.set('datetime', datetime))
 
     features = s2_masked.map(extract_features)
     fc = ee.FeatureCollection(features).filter(ee.Filter.notNull(['B2']))
@@ -95,9 +95,9 @@ def get_sentinel_bands_gee(
     rows = [f['properties'] for f in data['features']]
     df = pd.DataFrame(rows)
     if not df.empty:
-        df['date'] = pd.to_datetime(df['date'])
-        df = df.sort_values('date')
-        df = df.set_index('date')
+        df['datetime'] = pd.to_datetime(df['datetime'])
+        df = df.sort_values('datetime')
+        df = df.set_index('datetime')
     return df
 
 

{hydroanomaly-1.2.0.dist-info → hydroanomaly-1.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hydroanomaly
-Version: 1.2.0
+Version: 1.2.1
 Summary: A Python package for hydro anomaly detection with simple USGS data retrieval
 Author-email: Ehsan Kahrizi <ehsan.kahrizi@usu.edu>
 License: MIT License

hydroanomaly-1.2.1.dist-info/RECORD

@@ -0,0 +1,10 @@
+hydroanomaly/__init__.py,sha256=HgiUaNbWp_hAHaOvzCJXRBDwe89orkscx3Sd7lvgnQo,1664
+hydroanomaly/ml.py,sha256=X2bYinNwRzQz0yFtRSzmN8OIZaX7vfT4BPSE6KMoYAM,7066
+hydroanomaly/sentinel_bands.py,sha256=XdpXUsJ8VeRQp9akDeQaVBefuuMrQIabslu8tg_FTpk,5399
+hydroanomaly/usgs_turbidity.py,sha256=k0cXRXpTe1YgjfR0Htw77SLD8hM--43jiEiJwx1vRg0,5664
+hydroanomaly/visualize.py,sha256=d_Ou1sTr648TdAW-94NXwNbLPL4rvYVYb5pw4Xux3aE,7228
+hydroanomaly-1.2.1.dist-info/licenses/LICENSE,sha256=OphKV48tcMv6ep-7j-8T6nycykPT0g8ZlMJ9zbGvdPs,1066
+hydroanomaly-1.2.1.dist-info/METADATA,sha256=keF0Y92CYoZxOnU9vYaGfnefWr8s9mN7ncA2Qn2bp4I,12981
+hydroanomaly-1.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+hydroanomaly-1.2.1.dist-info/top_level.txt,sha256=t-5Lc-eTLlkxIhR_N1Cpp6_YZafKS3xLLk9D2CtbE7o,13
+hydroanomaly-1.2.1.dist-info/RECORD,,

hydroanomaly-1.2.0.dist-info/RECORD

@@ -1,10 +0,0 @@
-hydroanomaly/__init__.py,sha256=IGPsOv-xfQGQpr_HxhrcZXjvVVkAfMBxh97e6S8Rfac,1664
-hydroanomaly/ml.py,sha256=vqfnmGijjxGgtqJ2rzOmnMMrrVAVlYOPe1AnuX4EuG4,7018
-hydroanomaly/sentinel_bands.py,sha256=Y6RAunVJDYLs13WemSSQNEu07GqmhR64fC2mLPxwh2k,5371
-hydroanomaly/usgs_turbidity.py,sha256=k0cXRXpTe1YgjfR0Htw77SLD8hM--43jiEiJwx1vRg0,5664
-hydroanomaly/visualize.py,sha256=d_Ou1sTr648TdAW-94NXwNbLPL4rvYVYb5pw4Xux3aE,7228
-hydroanomaly-1.2.0.dist-info/licenses/LICENSE,sha256=OphKV48tcMv6ep-7j-8T6nycykPT0g8ZlMJ9zbGvdPs,1066
-hydroanomaly-1.2.0.dist-info/METADATA,sha256=bh51WnUxEbk3azZY2IN9a9Io1Pav7knU90qMiiiTGDU,12981
-hydroanomaly-1.2.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-hydroanomaly-1.2.0.dist-info/top_level.txt,sha256=t-5Lc-eTLlkxIhR_N1Cpp6_YZafKS3xLLk9D2CtbE7o,13
-hydroanomaly-1.2.0.dist-info/RECORD,,